clankermerge
Pass
Audited by Gen Agent Trust Hub on Oct 29, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from git conflict markers and source file contents during merge and rebase operations, which is a standard attack surface for development tools.
- Ingestion points: The agent reads conflicted file contents and hunk data within the
Rebase loopandMerge loopdescribed inSKILL.md. - Boundary markers: No explicit delimiters or instructions are provided to the agent to ignore instructions that might be embedded within the source code it analyzes during conflict resolution.
- Capability inventory: The skill enables the agent to execute git commands including
rebase,merge,add, andcommit, and to write resolved content to the local filesystem. - Sanitization: The agent does not perform sanitization on the hunk content before processing it for clustering or auto-resolution, though the
AskUserQuestionflow provides a manual verification step for complex hunks.
Audit Metadata